Provided herein is a sound output device 200 that includes a microphone 270, a speaker 280, and a processor 210. The sound output device 200 continues a conversation either autonomously or in accordance with an instruction from a server when the message accepted via the microphone 270 does not correspond to a first emotion, and ends a conversation either autonomously or in accordance with an instruction from a server when the message accepted via the microphone 270 corresponds to the first emotion.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A sound output device comprising: a microphone; a speaker; and a processor, wherein the processor is configured to continue a conversation with a user via the speaker when a message accepted via the microphone does not correspond to a first emotion, and to end a conversation with a user when a message accepted via the microphone corresponds to the first emotion; and wherein the processor is configured to execute the following acts: determining that the message does not correspond to the first emotion; generating a conversational output message comprising a repetition sentence and an emotion sentence; before ending the conversation, generating a check exit message and receiving a positive return message from the user.
A sound output device has a microphone, a speaker, and a processor. The processor continues a conversation via the speaker when the received message from the microphone doesn't express a "first emotion". When the microphone message expresses a "first emotion", the processor ends the conversation. To do this, the processor determines the message doesn't express the "first emotion", generates a conversational output including a repeated sentence and an emotion-related sentence. Before fully ending the conversation, the device asks a "check exit" question and waits for a positive response from the user.
2. The sound output device according to claim 1 , wherein the first emotion includes at least one of relief, content, curiosity, eagerness, happiness, affection, and respect, and wherein the processor is configured to determine that the message corresponds to the first emotion when the message contains a word that corresponds to at least one of relief, content, curiosity, eagerness, happiness, affection, and respect.
The sound output device from the previous description uses the following emotions as the "first emotion": relief, content, curiosity, eagerness, happiness, affection, or respect. The processor determines the message contains the "first emotion" if the message includes a word representing any of those emotions. Essentially, the device detects if the user expresses these emotions, and uses that to decide to end the conversation.
3. The sound output device according to claim 1 , wherein the processor is configured to continue a conversation via the speaker when any of a plurality of messages accepted a plurality of times via the microphone does not correspond to the first emotion, and wherein the processor is configured to end a conversation when a plurality of messages accepted a plurality of times via the microphone corresponds to the first emotion.
The sound output device from the first description continues a conversation if multiple messages received sequentially via the microphone do not express a "first emotion". The device ends the conversation only when multiple sequential messages express the "first emotion". Therefore, the device tracks emotion across multiple user inputs to determine when to end the conversation, not just a single message.
4. The sound output device according to claim 1 , wherein the processor is configured to continue a conversation via the speaker when at least one message accepted via the microphone during a predetermined time period does not correspond to the first emotion, and wherein the processor is configured to end a conversation when at least one message accepted via the microphone during the predetermined time period corresponds to the first emotion.
The sound output device from the first description monitors microphone input during a set time period. If any single message during that period doesn't contain the "first emotion", the conversation continues. If at least one message during that time contains the "first emotion", the conversation ends. The presence of the specific emotion during the defined window triggers the conversation's conclusion.
5. The sound output device according to claim 1 , wherein the processor is configured to continue a conversation via the speaker when at least a predetermined proportion of messages accepted a predetermined number of times via the microphone does not correspond to the first emotion, and wherein the processor is configured to end a conversation when at least a predetermined proportion of messages accepted the predetermined number of times via the microphone corresponds to the first emotion.
The sound output device from the first description continues the conversation if most of the messages over a defined number of messages do not include the "first emotion". The device ends the conversation when the defined proportion of those messages contains the "first emotion". It uses a ratio of emotion to determine whether to end the conversation, ensuring it only ends if the user expresses the target emotion frequently enough.
6. The sound output device according to claim 1 , wherein the processor is configured to continue a conversation via the speaker when at least a predetermined proportion of at least one message accepted via the microphone during a predetermined time period does not correspond to the first emotion, and wherein the processor is configured to end a conversation when at least a predetermined proportion of at least one message accepted via the microphone during a predetermined time period corresponds to the first emotion.
The sound output device from the first description monitors the messages inside of a period of time, and if a certain ratio of messages do not include the first emotion, the conversation continues. The device ends the conversation when the defined proportion of messages within that time contains the "first emotion". It determines the proportion of messages with the first emotion within that time period to decide whether or not to end the conversation.
7. The sound output device according to claim 1 , wherein the processor is configured to make the speaker output a message that agrees with the message input through the microphone.
The sound output device from the first description includes the speaker outputting a message that agrees with the message provided from the microphone. This agreement message would be performed before the determination of the continuation of the conversation is performed.
8. The sound output device according to claim 1 , wherein the processor is configured to make the speaker output a message that has substantially the same meaning as the message accepted via the microphone.
The sound output device from the first description outputs a message from the speaker that essentially means the same thing that was accepted via the microphone. This rephrasing happens before the continuation determination.
9. The sound output device according to claim 1 , wherein the processor is configured to make the speaker output a word that expresses an emotion corresponding to the message accepted via the microphone.
The sound output device from the first description uses its speaker to output a word showing the same emotion that was included in the microphone input. It identifies the emotion in the user's message and then vocalizes a word expressing the same emotion.
10. The sound output device according to claim 1 , wherein the processor in ending a conversation is configured to make the speaker output a message that indicates an upcoming action of the sound output device.
The sound output device from the first description alerts the user before ending the conversation by outputting a message. This end conversation message will tell the user of the action that is upcoming from the device.
11. The sound output device according to claim 1 , further comprising a communication interface for communicating with a server, wherein the processor received from the server via the communication interface a message to be output from the speaker.
The sound output device from the first description further incorporates a communication interface for communicating with a server. The processor can receive messages from this server using this interface that are then vocalized from the speaker.
12. A network system comprising: a sound output device that includes a microphone, a speaker, a first processor, and a first communication interface; and a server that includes a second processor, and a second communication interface for communicating with the sound output device, wherein the first processor is configured to send the server a message accepted via the speaker, the message being sent via the first communication interface, and wherein the second processor is configured to send data for continuing a conversation with a user to the sound output device via the second communication interface when the message received does not correspond to a first emotion, and to send data for ending a conversation with a user to the sound output device when the message received corresponds to the first emotion; and wherein the processor is configured to execute the following acts: determining that the message does not correspond to the first emotion; generating a conversational output message comprising a repetition sentence and an emotion sentence; before ending the conversation, generating a check exit message and receiving a positive return message from the user.
A network system contains a sound output device with a microphone, speaker, processor, and communication interface, and a server with a processor and communication interface. The sound output device sends messages to the server. The server sends the sound output device data to continue the conversation if the message does not correspond to the "first emotion". If it does, the server sends data to end the conversation. To do this, the processor determines the message doesn't express the "first emotion", generates a conversational output including a repeated sentence and an emotion-related sentence. Before fully ending the conversation, the device asks a "check exit" question and waits for a positive response from the user.
13. A server comprising: a communication interface for communicating with a sound output device; and a processor, wherein the processor is configured to receive a message from the sound output device via the communication interface, and wherein the processor is configured to cause via the communication interface the sound output device to continue a conversation with a user when the message does not correspond to a first emotion, and to end a conversation with a user when the message corresponds to the first emotion; and wherein the processor is configured to execute the following acts: determining that the message does not correspond to the first emotion; generating a conversational output message comprising a repetition sentence and an emotion sentence; before ending the conversation, generating a check exit message and receiving a positive return message from the user.
A server contains a communication interface for connecting with a sound output device and a processor. When the server receives a message from the sound output device, the server makes the device continue the conversation if the message doesn't express a "first emotion". If it expresses the "first emotion", the server instructs it to end the conversation. To do this, the processor determines the message doesn't express the "first emotion", generates a conversational output including a repeated sentence and an emotion-related sentence. Before fully ending the conversation, the device asks a "check exit" question and waits for a positive response from the user.
14. A sound output device comprising: a microphone; a speaker; and a processor, wherein the processor is configured to continue a conversation with a user via the speaker when a message accepted via the microphone corresponds to a second emotion, and wherein the processor is configured to end a conversation with a user when a message accepted via the microphone does not correspond to the second emotion; and wherein the processor is configured to execute the following acts: determining that the message corresponds to the second emotion; generating a conversational output message comprising a repetition sentence and an emotion sentence; before ending the conversation, generating a check exit message and receiving a positive return message from the user.
A sound output device has a microphone, a speaker, and a processor. The processor continues a conversation with a user if the message received from the microphone corresponds to a "second emotion". When the microphone input *doesn't* express the "second emotion", the processor ends the conversation. To do this, the processor determines the message expresses the "second emotion", generates a conversational output including a repeated sentence and an emotion-related sentence. Before fully ending the conversation, the device asks a "check exit" question and waits for a positive response from the user.
15. A network system comprising: a sound output device that includes a microphone, a speaker, a first processor, and a first communication interface; and a server that includes a second processor, and a second communication interface for communicating with the sound output device, wherein the first processor is configured to send the server a message accepted via the speaker, the message being sent via the first communication interface, and wherein the second processor is configured to send data for continuing a conversation with a user to the sound output device when the message received corresponds to a second emotion, and to send data for ending a conversation with a user to the sound output device when the message received does not correspond to the second emotion; and wherein the processor is configured to execute the following acts: determining that the message corresponds to the second emotion; generating a conversational output message comprising a repetition sentence and an emotion sentence; before ending the conversation, generating a check exit message and receiving a positive return message from the user.
A network system contains a sound output device and a server. The sound output device has a microphone, speaker, processor, and communication interface. The server has a processor and communication interface. The sound output device sends microphone messages to the server. The server tells the sound output device to continue the conversation if the message corresponds to a "second emotion". If it doesn't the server instructs it to end the conversation. To do this, the processor determines the message expresses the "second emotion", generates a conversational output including a repeated sentence and an emotion-related sentence. Before fully ending the conversation, the device asks a "check exit" question and waits for a positive response from the user.
16. A server comprising: a communication interface for communicating with a sound output device; and a processor, wherein the processor is configured to receive a message from the sound output device via the communication interface, and wherein the processor via the communication interface is configured to cause the sound output device to continue a conversation with a user when the message corresponds to a second emotion, and to end a conversation with a user when the message does not correspond to the second emotion; and wherein the processor is configured to execute the following acts: determining that the message corresponds to the second emotion; generating a conversational output message comprising a repetition sentence and an emotion sentence; before ending the conversation, generating a check exit message and receiving a positive return message from the user.
A server contains a communication interface for communicating with a sound output device, and a processor. When the server receives a message from the sound output device, the server instructs the sound output device to continue the conversation if the message corresponds to a "second emotion", and to end the conversation if it doesn't. To do this, the processor determines the message expresses the "second emotion", generates a conversational output including a repeated sentence and an emotion-related sentence. Before fully ending the conversation, the device asks a "check exit" question and waits for a positive response from the user.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
August 7, 2015
May 16, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.